OpenMMlab AI实战营第二期-第九次笔记

MMSegmentation代码课

预训练语义分割模型预测-视频

使用命令行

!python demo/video_demo.py \
        data/traffic.mp4 \
        configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py \
        https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth \
        --device cuda:0 \
        --output-file outputs/B3_video.mp4 \
        --opacity 0.5

使用Python API

导入工具包

import numpy as np
import time
import shutil

import torch

from PIL import Image
import cv2

import mmcv
import mmengine
from mmseg.apis import inference_model
from mmseg.utils import register_all_modules
register_all_modules()

from mmseg.datasets import CityscapesDataset

载入模型

# 模型 config 配置文件
config_file = 'configs/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024.py'

# 模型 checkpoint 权重文件
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/mask2former/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024/mask2former_swin-l-in22k-384x384-pre_8xb2-90k_cityscapes-512x1024_20221202_141901-dc2c2ddd.pth'

from mmseg.apis import init_model
model = init_model(config_file, checkpoint_file, device='cuda:0')

from mmengine.model.utils import revert_sync_batchnorm
if not torch.cuda.is_available():
    model = revert_sync_batchnorm(model)

输入视频路径

# input_video = 'data/traffic.mp4'

input_video = 'data/street_20220330_174028.mp4'

创建临时文件夹，存放每帧结果

temp_out_dir = time.strftime('%Y%m%d%H%M%S')
os.mkdir(temp_out_dir)
print('创建临时文件夹 {} 用于存放每帧预测结果'.format(temp_out_dir))

视频单帧预测

# 获取 Cityscapes 街景数据集 类别名和调色板
from mmseg.datasets import cityscapes
classes = cityscapes.CityscapesDataset.METAINFO['classes']
palette = cityscapes.CityscapesDataset.METAINFO['palette']

def pridict_single_frame(img, opacity=0.2):
    
    result = inference_model(model, img)
    
    # 将分割图按调色板染色
    seg_map = np.array(result.pred_sem_seg.data[0].detach().cpu().numpy()).astype('uint8')
    seg_img = Image.fromarray(seg_map).convert('P')
    seg_img.putpalette(np.array(palette, dtype=np.uint8))
    
    show_img = (np.array(seg_img.convert('RGB')))*(1-opacity) + img*opacity
    
    return show_img

视频逐帧预测

# 读入待预测视频
imgs = mmcv.VideoReader(input_video)

prog_bar = mmengine.ProgressBar(len(imgs))

# 对视频逐帧处理
for frame_id, img in enumerate(imgs):
    
    ## 处理单帧画面
    show_img = pridict_single_frame(img, opacity=0.15)
    temp_path = f'{temp_out_dir}/{frame_id:06d}.jpg' # 保存语义分割预测结果图像至临时文件夹
    cv2.imwrite(temp_path, show_img)

    prog_bar.update() # 更新进度条

# 把每一帧串成视频文件
mmcv.frames2video(temp_out_dir, 'outputs/B3_video.mp4', fps=imgs.fps, fourcc='mp4v')

shutil.rmtree(temp_out_dir) # 删除存放每帧画面的临时文件夹
print('删除临时文件夹', temp_out_dir)